symbiont
**Purpose**: This guide helps AI assistants quickly build secure, compliant Symbiont agents following best practices.
Setup & Installation
Install command
clawhub install jaschadub/symbiontIf the CLI is not installed:
Install command
npx clawhub@latest install jaschadub/symbiontOr install with OpenClaw CLI:
Install command
openclaw skills install jaschadub/symbiontor paste the repo link into your assistant's chat
Install command
https://github.com/openclaw/skills/tree/main/skills/jaschadub/symbiontWhat This Skill Does
Symbiont is an agent runtime for building secure, policy-enforced AI agents using a declarative DSL. It implements a typestate-enforced ORGA reasoning loop (Observe-Reason-Gate-Act), Cedar-based authorization, and multi-tier sandboxing via Docker, gVisor, and Firecracker. Compliance patterns for HIPAA, SOC2, and GDPR are built in.
Policy enforcement happens at the framework level via Cedar authorization and compile-time phase transitions, so security rules cannot be bypassed by mistakes in agent logic.
When to Use It
- Processing GitHub webhook events with HMAC signature verification
- Running scheduled data archival or cleanup agents on cron schedules
- Orchestrating multi-step workflows with failure recovery and circuit breakers
- Building parallel API aggregators that call multiple external services
- Scanning codebases for vulnerabilities inside isolated gVisor sandboxes
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Processing GitHub webhook events with HMAC signature verification
- 1Processing GitHub webhook events with HMAC signature verification
- 2Running scheduled data archival or cleanup agents on cron schedules
- 3Orchestrating multi-step workflows with failure recovery and circuit breakers
- 4Building parallel API aggregators that call multiple external services
- 5Scanning codebases for vulnerabilities inside isolated gVisor sandboxes
**Purpose**: This guide helps AI assistants quickly build secure, compliant Symbiont agents following best practices.
Security Audits
These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.